检索结果-内蒙古大学图书馆

2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022

作者： Chen, Diliang Ghoreishi, Nozhan Olugbon, Femi Ansah, Stella Huang, Ming-Chun Yu, Qiaoyan University of New Hampshire Electrical and Computer Engineering Durham United States Duke Kunshan University Data and Computational Science Suzhou China

ISBN: (数字)9781665469173

ISBN: (纸本)9781665469173

Heel-strike and toe-off are important gait events for gait analysis. Smart insoles with pressure sensors in different locations have been proposed to detect these two gait events. However, there is no research to reveal optimal sensor locations under the foot for heel-strike and toe-off detection. To address this problem, a novel method based on the mechanism of heel-strike and toe-off detection was proposed to find out the optimal sensor locations. A smart insole system, which has 96 pressure sensors uniformly distributed on it, was used to supply ground truth. Experiment data was collected from six subjects, each of whom wore a pair of smart insoles and walked 15 steps at their comfort speeds. The results showed that two top optimal pressure locations identified with the proposed method were enough to detect heel-strike and toe-off with good accuracy. Options of top optimal sensor locations for heel-strike and toe-off detection were mainly concentrated in the middle of the heel area (sensors 5, 6, 8, 10, 11, 13, and 14) and the front edge of the metatarsal bone area (sensors 55, 59, 60, and 61), respectively. This research provided references for future researchers to effectively use pressure sensors for smart insole design and gait analysis. © 2022 IEEE.

关键词： Pressure sensors

来源：评论

学校读者我要写书评

暂无评论

Joint Multi-Scale Contextual and Noise Suppression for Group Emotion Recognition

Joint Multi-Scale Contextual and Noise Suppression for Group...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guo, Wangdong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Group Emotion Recognition (GER) seeks to identify emotional states within multi-person groups. The complexity of the environment and the reliance on a single group emotion label often result in noisy individuals with inconsistent emotional expressions, hampering accurate emotion classification. Mainstream GER networks attempt to downweight noisy individuals, but when their numbers are high and over-relying on a single group label, the negative impact of noise on individuals remains significant, further complicating classification and diminishing accuracy. To address these limitations, we propose the Multi-Scale Contextual and Noise Suppression Model (MCon-NSM), a novel framework that enhances GER by capturing fine-grained interaction contexts and collaboratively suppressing noise at both the individual and group label levels. Extensive experiments on the GAF series datasets demonstrate that our method achieves results comparable to state-of-the-art techniques, validating its effectiveness in mitigating noise in GER. © 2025 IEEE.

关键词： Emotion analysis Group emotion recognition Multi-Scale context learning Noise suppression

来源：评论

学校读者我要写书评

暂无评论

Improving the Efficiency of Multimodal Approach for Chest X-Ray 2nd

Improving the Efficiency of Multimodal Approach for Chest...

引用

2nd International Conference on Advances in Computing Research, ACR 2024

作者： Upadhya, Jiblal Vargas, Jorge Poudel, Khem Ranganathan, Jaishree Computational and Data Science Middle Tennessee State University MurfreesboroTN37132 United States Department of Engineering Technology Middle Tennessee State University MurfreesboroTN37132 United States Department of Computer Science Middle Tennessee State University MurfreesboroTN37132 United States

ISBN: (纸本)9783031569494

Medical data analysis with limited data has been a challenging problem in machine learning. Privacy regulations limit the sharing and use of patient data, making it challenging to access and aggregate large datasets for research purposes. To address this challenge, we propose a deep learning-based Multimodal network that incorporates data from multiple data sources: images, and text in the learning process. When faced with limited data of one type, incorporating data from multiple sources can enhance the model’s performance and generalization. Our approach integrates the text sub-model and image sub-model with deep network of Dense 512 using the transfer learning process. Specifically, the goal is to explore the impact of hyperparameter adjustments on the performance of the model with different learning rates. Evaluation of our proposed approach on the Indiana University Chest X-ray dataset that consists of textual (radiological reports) and visual (X-ray images) show that our approach significantly outperforms several baseline methods in classification accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Integrating Instruction-based Learning with Bidirectional LSTM for Autonomous Vehicle Pedestrian Detection

Integrating Instruction-based Learning with Bidirectional LS...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Shoba, B. Raghunathan, T. Peter, S.Sam Karthick, K. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak Psn College of Engineering and Technology Department of Electronics and Communication Engineering Tirunelveli India Dr.NG.p.Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Sri Krishna College of Technology Department of Computer Science and Engineering Coimbatore India Sona College of Technology Department of Information Technology Salem India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

Pedestrian detection is a crucial aspect of autonomous vehicle (A V) safety, as it enables accurate identification and tracking of individuals in an A V environment. Effective pedestrian detection supports essential A V functions like braking, steering, and speed control to prevent accidents in urban settings. Traditional computer vision methods, such as Support Vector Machines and Random Forests, rely on pre-designed features like the Histogram of Oriented Gradients. While the existing techniques offer some performance, it face significant challenges in dynamic environments, especially under varying lighting conditions, occlusions, and diverse pedestrian poses. Traditional models also require extensive manual feature engineering and tuning, which limits scalability and adaptability. Recent advances in deep learning, particularly with Convolutional Neural Networks (CNNs), have allowed for automatic feature learning, yielding practical improvements over classical methods. However, CNNs can struggle in low light and when facing adversarial attacks, as they mainly capture spatial features. To address these limitations, this research proposes a new methodology combining CNNs for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to capture temporal dependencies. This hybrid approach enhances detection capabilities by learning both static and dynamic patterns. Our proposed CNN-BiLSTM model achieves a 92 % detection accuracy and an F1 score of 88.5% across diverse conditions, outperforming existing models by up to 15%. By integrating temporal features, the model reduces missed detections and false positives by up to 20%, providing a more reliable and adaptable solution for pedestrian detection in autonomous vehicles. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel myocarditis detection combining deep reinforcement learning and an improved differential evolution algorithm

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1347-1360页

作者： Jing Yang Touseef Sadiq Jiale Xiong Muhammad Awais Uzair Aslam Bhatti Roohallah Alizadehsani Juan Manuel Gorriz Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversiti MalayaKuala LumpurMalaysia Centre for Artificial Intelligence Research(CAIR) Department of Information and Communication TechnologyUniversity of AgderGrimstadNorway Department of Creative Technologies Air UniversityIslamabadPakistan School of Information and Communication Engineering Hainan UniversityHaikouHainanChina Institute for Intelligent Systems Research and Innovation(IISRI) Deakin UniversityWaurn PondsVictoriaAustralia Data Science and Computational Intelligence Institute University of GranadaGranadaSpain

Myocarditis is a serious cardiovascular ailment that can lead to severe consequences if not promptly *** is triggered by viral infections and presents symptoms such as chest pain and heart *** detection is crucial for successful treatment,and cardiac magnetic resonance imaging(CMR)is a valuable tool for identifying this ***,the detection of myocarditis using CMR images can be challenging due to low contrast,variable noise,and the presence of multiple high CMR slices per *** overcome these challenges,the approach proposed incorporates advanced techniques such as convolutional neural networks(CNNs),an improved differential evolution(DE)algorithm for pre-training,and a reinforcement learning(RL)-based model for *** this method presented a significant challenge due to the imbalanced classification of the Z-Alizadeh Sani myocarditis dataset from Omid Hospital in *** address this,the training process is framed as a sequential decision-making process,where the agent receives higher rewards/penalties for correctly/incorrectly classifying the minority/majority ***,the authors suggest an enhanced DE algorithm to initiate the backpropagation(BP)process,overcoming the initialisation sensitivity issue of gradient-based methods like back-propagation during the training *** effectiveness of the proposed model in diagnosing myocarditis is demonstrated through experimental results based on standard performance ***,this method shows promise in expediting the triage of CMR images for automatic screening,facilitating early detection and successful treatment of myocarditis.

关键词： classification differential evolution myocarditis reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Pelvic bone region segmentation (PBRS) from X-ray image using convolutional neural network (CNN) 26

Pelvic bone region segmentation (PBRS) from X-ray image usin...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Ul Alam, Syed Alif Binte Alam, Saadia Saha, Sourav Haque, Mahmudul Rahman, Rashedur Kobashi, Syoji Independent University Bangladesh Department of Computer Science and Engineering Dhaka1229 Bangladesh Independent University Bangladesh Center for Computational & Data Sciences Dhaka1229 Bangladesh University of Hyogo Graduate School of Engineering Shosha Hyogo Himeji2167 Japan

ISBN: (纸本)9798350359015

Pelvic and hip fractures offer considerable public health risks with high morbidity and mortality rates. Because of the complicated bone structure of the pelvic bone region, detecting fractures is difficult. Though X-ray imaging is routinely utilised for detecting fractures, manual fracture diagnosis is prone to inaccuracies. This paper proposes the use of deep learning algorithms for automated segmentation of the pelvic bone region in X-ray images. In our work, we have investigated U-Net based pelvic area segmentation models with various convolutional neural network (CNN) backbones. The DenseNet121-based U-Net design emerged as the most optimal model, establishing a compromise between performance and computational efficiency. Although it had a modest loss in IoU and F1 scores when compared to InceptionNetV3, it had a remarkable 59.44% reduction in the number of parameters. © 2023 IEEE.

关键词： deep learning pelvic bone segmentation x-ray

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

Mesoscale Wind Farm Placement via Linear Optimization Constrained by Power System and Techno-economics

引用

Journal of Modern Power Systems and Clean Energy 2021年第2期9卷 356-366页

作者： Ali Erduman Bahri Uzunoglu Bedri Kekezoglu Ali Durusu the Electrical Engineering Department Hakkari UniversityHakkari30000 Turkey Department of Engineering Sciences Department of Electrical EngineeringComputational and Data-enabled Science and Engineering in Energy SystemsUppsala University75121 UppsalaSweden Department of Mathematics Florida State UniversityTallahasseeFL 32310USA the Electrical Engineering Department Yildiz Technical UniversityIstanbul34220 Turkey

The objective of this study is to develop a wind farm placement and investment methodology based on a linear optimization *** problem has a major significance for the investment success for the projects of renewable energy such as wind *** this study,a mesoscale approach is adopted whereby the wind farm location is investigated in comparison with a microscale approach where the location of each individual turbine is *** study focuses on the placement of a wind farm by economical optimization constrained by the power system,wind resources,and *** optimization is introduced in this context at the power system which is constrained by wind farm planning.

关键词： Generation expansion grid integration mesoscale wind farm linear optimization wind power

来源：评论

学校读者我要写书评

暂无评论

Personalized Stress Detection using a Lightweight Machine Learning Framework With Convenient Wrist-Worn Sensors

Personalized Stress Detection using a Lightweight Machine Le...

引用

2024 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2024

作者： Hasan, M. Mithun, S. Mahmud, M. Baral, S. Poudel, K. Middle Tennessee State University Computational And Data Science MurfreesboroTN United States University Of Memphis Dept. Of Computer Science TN United States University Of Memphis Dept. Of Electrical And Computer Engineering TN United States Middle Tennessee State University Dept. Of Computer Science MurfreesboroTN United States Univ. Of Tennessee Health Science Center Div. Of General Internal Medicine MemphisTN United States

ISBN: (纸本)9798350388572

Over 70% Americans experience daily stress, making real-time, accurate stress detection crucial for timely intervention, and promoting physical and mental well-being. In this study, we detect stress using machine learning from publicly available wrist-worn sensor data. We examined both population and individual levels, focusing on simple, computation friendly statistical features for reduced processing to facilitate adoptions in real-life mHealth applications. Our framework demonstrates that stress detection achieves over 96% accuracy at both the population and individual levels, with the Extreme Gradient Boosting classifier achieving the highest predictive accuracy. We found significant variability between individuals and achieved an average accuracy of 99.63% with area under the curve (AUC) 99.23%, F1-score 99.00%, precision, and recall 99.22%. This approach offers a promising solution for real-life stress detection due to its high accuracy and simplicity. © 2024 IEEE.

关键词： LightGBM Machine learning Personalization Stress detection Wrist-band sensors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Chronic Kidney Disease Prediction Through data Preprocessing Optimization and Machine Learning Techniques

Enhancing Chronic Kidney Disease Prediction Through Data Pre...

引用

2023 IEEE International Conference on Electrical, computer and Energy Technologies, ICECET 2023

作者： Akinyemi, Lateef Adesola Oshinuga, Olamide Peter Ekwe, Stephen Obono Oladejo, Sunday Oladayo University of South Africa Cset Department of Compt. Science & Electrical Engineering Johannesburg South Africa Lagos State University Department of Electronic and Computer Engineering Lagos Nigeria Cape Peninsula University of Technology Department of Elect. Electronic and Computer Engineering Cape Town South Africa School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa

ISBN: (纸本)9798350327816

Health care is the improvement of health through the avoidance and cure of diseases. Chronic kidney disease (CKD) poses a substantial health issue, ranking as the eighth leading cause of death and the tenth leading cause of disability-adjusted life years for both genders. This research aims to utilize machine learning (ML) algorithms to accurately predict the presence of CKD, which affects people worldwide. Timely identification of CKD is crucial to prevent it from progressing to its final and most critical phase. Machine learning algorithms, such as Decision Tree (DT), Naïve Bayes (NB), and others, are used in this study for the prediction of CKD. Various health parameters such as age, albumin level, and more are used as input into each ML algorithm to predict the presence of CKD. data preprocessing is carried out to improve the quality of the data for more accurate prediction. The data is analyzed to uncover the connections between CKD health parameters and their impact on the occurrence of CKD. This research further examines the influence of different train and test data ratios on the accuracy of the employed algorithms. Evaluation metrics such as accuracy, sensitivity, and more are employed to gauge the effectiveness of each algorithm in making predictions. Random Forest stood out as the most accurate algorithm, with a score of 96.25%. Naive Bayes and XGBoost demonstrated the highest sensitivity, achieving a perfect score of 100%. © 2023 IEEE.

关键词： Chronic Kidney Disease (CKD) data Analysis data Preprocessing Health Care Machine Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：